Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "im-" indicating transformation or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ________________
    -0.18
    IPH
    -0.16
    ond
    -0.15
    Disclosure
    -0.14
     Crimes
    -0.14
    Pad
    -0.14
    nic
    -0.14
    kup
    -0.14
    appen
    -0.14
    age
    -0.14
    POSITIVE LOGITS
    manuel
    0.18
    agination
    0.17
    ortal
    0.17
    ortality
    0.16
    anzi
    0.16
    ochen
    0.16
    angl
    0.16
    ÑĥÑīеÑģÑĤв
    0.15
    enez
    0.15
    iesz
    0.15
    Act Density 0.151%

    No Known Activations